MCP Review Code Tool
A code review tool based on Model Context Protocol (MCP) that leverages OpenAI's capabilities for intelligent code analysis and review. | 基于模型上下文协议(MCP)的代码审查工具，利用OpenAI的能力进行智能代码分析和审查。
What is MCP Review Code Tool?
MCP Review Code Tool is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to code review tool based on model context protocol (mcp) that leverages openai's capabilities for intelligent code analysis and review. | 基于模型上下文协议(mcp)的代码审查工具，利用openai的能力进行智能代码分析和审查。
A code review tool based on Model Context Protocol (MCP) that leverages OpenAI's capabilities for intelligent code analysis and review. | 基于模型上下文协议(MCP)的代码审查工具，利用OpenAI的能力进行智能代码分析和审查。
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A code review tool based on Model Context Protocol (MCP) tha
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mcp-review-code-toolConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use MCP Review Code Tool
MCP Review Code Tool is a code review server built on the Model Context Protocol that leverages OpenAI-compatible APIs (including OpenRouter) to perform intelligent analysis of your source code. It integrates directly into MCP clients like Claude and exposes a review tool that evaluates code quality, detects issues, and suggests improvements. A companion web interface supports multi-file uploads and visual reporting, making it useful for development teams who want AI-powered code review embedded in their editor or CI workflow.
Prerequisites
- Node.js 18+ and npm installed (nvm recommended for version management)
- An OpenAI API key or an OpenRouter account with an API key for accessing code-review models
- Git for cloning the repository
- An MCP-compatible client such as Claude Desktop or Claude Code
Clone the repository
Clone the mcp_review_code_tool repository to your local machine.
git clone https://github.com/wenkil/mcp_review_code_tool.git
cd mcp_review_code_toolInstall dependencies
Install all required npm packages.
npm installBuild the TypeScript project
Compile the TypeScript source to the dist directory. The MCP server entry point will be at dist/mcp_code_review.js.
npm run buildGather your API credentials
You will need an OPENAI_API_KEY and the base URL of your provider. When using OpenRouter, set OPENAI_API_BASE to https://openrouter.ai/api/v1. The default model is qwen/qwen-2.5-coder-32b-instruct:free but can be overridden.
Configure the MCP client
Add the server to your MCP client config (mcp.json or claude_desktop_config.json), providing the absolute path to the compiled JS file and your API credentials as environment variables.
{
"mcpServers": {
"code-review": {
"command": "node",
"args": ["/absolute/path/to/mcp_review_code_tool/dist/mcp_code_review.js"],
"cwd": "/absolute/path/to/mcp_review_code_tool",
"env": {
"OPENAI_API_KEY": "your_api_key_here",
"OPENAI_API_BASE": "https://openrouter.ai/api/v1",
"OPENAI_API_MODEL": "qwen/qwen-2.5-coder-32b-instruct:free"
}
}
}
}Restart your MCP client and test the review tool
Restart Claude Desktop or your chosen client. The code review tool should now be available. Paste code into your prompt and ask for a review.
MCP Review Code Tool Examples
Client configuration
Claude Desktop configuration using node to run the compiled MCP code review server with OpenRouter credentials.
{
"mcpServers": {
"code-review": {
"command": "node",
"args": ["/absolute/path/to/mcp_review_code_tool/dist/mcp_code_review.js"],
"cwd": "/absolute/path/to/mcp_review_code_tool",
"env": {
"OPENAI_API_KEY": "your_api_key_here",
"OPENAI_API_BASE": "https://openrouter.ai/api/v1",
"OPENAI_API_MODEL": "qwen/qwen-2.5-coder-32b-instruct:free"
}
}
}
}Prompts to try
Example prompts for requesting code reviews through the MCP tool.
- "Review this Python function for bugs and suggest improvements: [paste code]"
- "Check this JavaScript module for security vulnerabilities"
- "Analyze the code quality of this TypeScript class and rate it"
- "What are the performance issues in this SQL query?"
- "Review my Go HTTP handler for best practices and error handling"Troubleshooting MCP Review Code Tool
API authentication errors when calling the review tool
Verify that OPENAI_API_KEY is correct and that OPENAI_API_BASE matches your provider. For OpenRouter, the base URL must be https://openrouter.ai/api/v1 exactly — no trailing slash.
Cannot find module at dist/mcp_code_review.js
The TypeScript source has not been compiled. Run `npm run build` in the project directory first. Verify the dist/ folder exists and contains mcp_code_review.js before restarting the MCP client.
Model returns empty or truncated reviews
Switch to a model with a larger context window by setting OPENAI_API_MODEL in your config. Long files may exceed the free model's token limit — consider gpt-4o or claude-3-5-sonnet via OpenRouter for more thorough reviews.
Frequently Asked Questions about MCP Review Code Tool
What is MCP Review Code Tool?
MCP Review Code Tool is a Model Context Protocol (MCP) server that code review tool based on model context protocol (mcp) that leverages openai's capabilities for intelligent code analysis and review. | 基于模型上下文协议(mcp)的代码审查工具，利用openai的能力进行智能代码分析和审查。 It connects AI assistants to external tools and data sources through a standardized interface.
How do I install MCP Review Code Tool?
Follow the installation instructions on the MCP Review Code Tool GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with MCP Review Code Tool?
MCP Review Code Tool works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is MCP Review Code Tool free to use?
Yes, MCP Review Code Tool is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
MCP Review Code Tool Alternatives — Similar Coding Agents Servers
Looking for alternatives to MCP Review Code Tool? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up MCP Review Code Tool in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use MCP Review Code Tool?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.